by Martina Megaro | Jun 10, 2019 | Machine Learning
Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation We propose a novel,polynomial-time approximation of Shapley values in deep neural networks. June 10, 2019International Conference on Machine Learning (ICML) 2019 ...
by Martina Megaro | Jun 1, 2019 | Animation, Story Technology, Visual Computing
Generating Animations from Screenplays In this paper, we develop a text-to-animation system which is capable of handling complex sentences. June 1, 2019*SEM 2019 Authors Yeyao Zhang (Disney Research/ETH Joint M.Sc.) Eleftheria Tsipidi (Disney Research) Sasha...
by Martina Megaro | May 28, 2019 | Machine Learning, Video Processing, Visual Computing
Learning-based Sampling for Natural Image Matting We present a new sampling-based natural matting tech- nique that utilizes a pair of novel sampling networks for estimating background and foreground colors of pixels in unknown image regions. June 16, 2019IEEE...
by Martina Megaro | May 6, 2019 | Capture, VFX, Visual Computing
Practical Person-Specific Eye Rigging We present a novel parametric eye rig for eye animation, including a new multi-view imaging system that can reconstruct eye poses at submillimeter accuracy to which we fit our new rig. May 6, 2019Eurographics 2019 Authors...
by Martina Megaro | Apr 30, 2019 | Rendering, VFX, Visual Computing
Analysis of Sample Correlations for Monte Carlo Rendering In this paper, we aim at providing a comprehensive and accessible overview of the techniques developed over the last decades to analyze such correlations, relate them to error in integrators, and understand...
